UAS Navigation in the Real World Using Visual Observation

TL;DR

This paper introduces a novel end-to-end visual navigation system for UAS that combines reinforcement learning and image matching, enabling real-world long-range navigation using only a single camera.

Contribution

It presents a dual-phase navigation approach inspired by human vision, integrating RL-trained policies with real-world landmark recognition for UAS.

Findings

UAS can navigate hundreds of meters using only visual input.

The system successfully combines RL and image matching for real-world navigation.

UAS achieves shortest path navigation in real-world scenarios.

Abstract

This paper presents a novel end-to-end Unmanned Aerial System (UAS) navigation approach for long-range visual navigation in the real world. Inspired by dual-process visual navigation system of human's instinct: environment understanding and landmark recognition, we formulate the UAS navigation task into two same phases. Our system combines the reinforcement learning (RL) and image matching approaches. First, the agent learns the navigation policy using RL in the specified environment. To achieve this, we design an interactive UASNAV environment for the training process. Once the agent learns the navigation policy, which means 'familiarized themselves with the environment', we let the UAS fly in the real world to recognize the landmarks using image matching method and take action according to the learned policy. During the navigation process, the UAS is embedded with single camera as the only visual sensor. We demonstrate that the UAS can learn navigating to the destination hundreds meters away from the starting point with the shortest path in the real world scenario.